Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Heads
It provides a lightweight, plug-and-play solution for real-time hallucination detection in white-box LLMs, addressing the need for efficient uncertainty quantification without supervision.
The paper proposes RAUQ, an unsupervised and efficient framework for detecting hallucinations in LLMs by leveraging uncertainty-aware attention heads, achieving state-of-the-art performance across twelve datasets and nine LLMs with less than 1% additional computation.
While large language models (LLMs) have become highly capable, they remain prone to factual inaccuracies, commonly referred to as "hallucinations." Uncertainty quantification (UQ) offers a promising way to mitigate this issue, but most existing methods are computationally intensive and/or require supervision. In this work, we propose Recurrent Attention-based Uncertainty Quantification (RAUQ), an unsupervised and efficient framework for identifying hallucinations. The method leverages an observation about transformer attention behavior: when incorrect information is generated, certain "uncertainty-aware" attention heads tend to reduce their focus on preceding tokens. RAUQ automatically detects these attention heads and combines their activation patterns with token-level confidence measures in a recurrent scheme, producing a sequence-level uncertainty estimate in just a single forward pass. Through experiments on twelve datasets spanning question answering, summarization, and translation across nine different LLMs, we show that RAUQ consistently outperforms state-of-the-art UQ baselines. Importantly, it incurs minimal overhead, requiring less than 1\% additional computation. Since it requires neither labeled data nor extensive parameter tuning, RAUQ serves as a lightweight, plug-and-play solution for real-time hallucination detection in white-box LLMs.